Ke Pan
Xidian University
13 Papers
24 Citations
Ke Pan is an academic researcher from Xidian University. The author has contributed to research in topics: Computer science & Differential privacy. The author has an hindex of 4, co-authored 9 publications.
Chat about Author
Papers
A Survey on Differentially Private Machine Learning [Review Article]
TL;DR: This work provides a comprehensive survey on the existing works that incorporate differential privacy with machine learning, so- called differentially private machine learning and categorizes them into two broad categories as per different differential privacy mechanisms: the Laplace/ Gaussian/exponential mechanism and the output/objective perturbation mechanism.
104
Preserving differential privacy in deep neural networks with relevance-based adaptive noise imposition.
TL;DR: A general differentially private deep neural networks learning framework based on relevance analysis, which aims to bridge the gap between private and non-private models while providing an effective privacy guarantee of sensitive information.
59
Chinese Named Entity Recognition Based on Rules and Conditional Random Field
Weiming Liu,Bin Yu,Chen Zhang,Han Wang,Ke Pan +4 more
- 08 Dec 2018
TL;DR: A Chinese named entity recognition method based on rules and conditional random fields based on the analysis of the actual characteristics of named entities in Chinese text can effectively identify the named entities, improve the processing speed and efficiency, and has certain practical value.
14
Node proximity preserved dynamic network embedding via matrix perturbation
TL;DR: The proposed Node Proximity Preserved Dynamic Network Embedding via Matrix Perturbation (NPDNE) implements a low-rank transformation on the normalized Laplacian matrix of the given networks and derives the embedding vectors through generalized SVD, which reveals the intrinsic relationship among different-order proximities.
11
Differentially private regression analysis with dynamic privacy allocation
TL;DR: In this paper, an adaptive differentially private regression model is proposed to enhance the security guarantee without sacrificing plenty of model utility, which allocates the privacy budget dynamically by using the relevance-based noise imposition mechanism.
11